A team-based process for reviewing a GitHub pull request, which is a proposed code change, with several specialist reviewers and one reviewer who challenges their findings.

Use it before merging important pull requests, especially large features, infrastructure changes, or changes with ticket requirements. It accepts a pull-request URL or number and can check acceptance criteria when ticket context is available.

It filters out weak or false-positive comments by making reviewers defend, revise, or withdraw their findings before the final report.

review-team — Skill for Claude Code by EricTechPro

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add EricTechPro/startup-claude-skills --skill review-team

Clone the repo

git clone --depth 1 https://github.com/EricTechPro/startup-claude-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-team/github.svg)](https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-team)

Your own site

<a href="https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-team"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-team/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-team"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,421 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.07421
Opus 5	$0.00024	$0.03710
Sonnet 5	$0.00010	$0.01484
Haiku 4.5	$0.00005	$0.00742

Measured 10d ago against content hash 00caa59a4e81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/review-team/SKILL.md · 840 lines

How it starts

The opening of the file, as written. The whole thing — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Team with Devil's Advocate

Orchestrate a team-based PR review using Agent Teams (TeamCreate + SendMessage). Four specialist reviewers analyze a GitHub PR, then a Devil's Advocate challenges every finding. Original reviewers must defend, adjust, or withdraw. Only surviving findings — with confidence ratings — appear in the final report.

When to Use This Skill

Before merging a PR - Get high-confidence, adversarially filtered feedback
For critical PRs - When false positives are costly (large features, infra changes)
When you want fewer, better findings - Devil's Advocate filters noise
For PRs with ticket context - Auto-detects ticket for acceptance criteria validation

Parameters

Parameter	Default	Description
(first arg)	required	PR URL or PR number
`ticket`	auto-detect	Ticket key override (e.g., `ticket=PROJ-94`)
`skip-challenge`	`false`	Skip Devil's Advocate phase (degrades to standard parallel review)
`verbose`	`false`	Include full challenge/defense transcript in report

Invocation

/review-team https://github.com/owner/repo/pull/123
/review-team 123
/review-team 123 ticket=PROJ-94
/review-team 123 skip-challenge=true
/review-team 123 verbose=true

Architecture

ORCHESTRATOR (main session - team lead, manages state + synthesis)
|
+-- Phase 0: INIT
|   Parse PR URL, fetch metadata + diff, auto-detect ticket
|   Read CLAUDE.md for project conventions
|   TeamCreate("pr-review-{number}")
|
+-- Phase 1: TASK CREATION
|   Create 5 tasks in shared task list (TaskCreate)
|   Assign 4 reviewer tasks to specialist teammates
|
+-- Phase 2: PARALLEL REVIEW (4 agents work simultaneously)
|   +-- staff-engineer      (code-refactorer)
|   +-- qa-engineer          (general-purpose)
|   +-- security-reviewer    (general-purpose)
|   +-- architect            (system-architect)
|   Each sends findings JSON to team lead via SendMessage
|
+-- Phase 3: DEVIL'S ADVOCATE CHALLENGE
|   +-- devils-advocate      (general-purpose)
|   Receives ALL aggregated findings from Phase 2
|   Sends targeted challenges to each original reviewer
|
+-- Phase 4: DEFENSE / REBUTTAL (4 agents respond)
|   Each reviewer: DEFEND / ADJUST / WITHDRAW
|   Sends responses to devils-advocate
|
+-- Phase 5: VERDICT
|   devils-advocate assigns confidence ratings
|   Sends final verdict to team lead
|
+-- Phase 6: SYNTHESIS
|   Build unified report, shutdown teammates, TeamDelete
|   Present report to user
|
+-- STATE: .review-team/state.json

Read the full file on GitHub · 840 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 840 lines · 48 tokens per session scan A 00caa59a4e81

Subscribe to this mod's changes

review-team is a skill published in the GitHub repository EricTechPro/startup-claude-skills (55 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 7,421 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens